@inproceedings{bassanini-etal-2026-quid,
title = "Quid est {VERITAS}? A Modular Framework for Archival Document Analysis",
author = "Bassanini, Leonardo and
Biancardi, Ludovico and
Ferrara, Alfio and
Gamberini, Andrea and
Picascia, Sergio and
Vaglienti, Folco",
editor = "Montejo-Raez, Arturo and
Grisot, Cristina and
Blochowiak, Joanna and
Ljube{\v{s}}i{\'c}, Nikola and
Battaner, Elena and
Rigau, German",
booktitle = "Proceedings of Shaping Multilingual, Multimodal {AI} for the Social Sciences and Humanities ({LLM}s4{SSH}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma de Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.llms4ssh-1.6/",
doi = "10.63317/3ec9hbgdgs8x",
pages = "57--66",
abstract = "The digitisation of historical documents has traditionally been conceived as a process limited to character-level transcription, producing flat text that lacks the structural and semantic information necessary for substantive computational analysis. We present VERITAS (Vision-Enhanced Reading, Interpretation, and Transcription of Archival Sources), a modular, model-agnostic framework that reconceptualises digitisation as an integrated workflow encompassing transcription, layout analysis, and semantic enrichment. The pipeline is organised into four stages{---}Preprocessing, Extraction, Refinement, and Enrichment{---}and employs a schema-driven architecture that allows researchers to declaratively specify their extraction objectives. We evaluate VERITAS on the critical edition of Bernardino Corio{'}s Storia di Milano, a Renaissance chronicle of over 1,600 pages. Results demonstrate that the pipeline achieves a 67.6{\%} relative reduction in word error rate compared to a commercial OCR baseline, with a threefold reduction in end-to-end processing time when accounting for manual correction. We further illustrate the downstream utility of the pipeline{'}s output by querying the transcribed corpus through a retrieval-augmented generation system, demonstrating its capacity to support historical inquiry."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bassanini-etal-2026-quid">
<titleInfo>
<title>Quid est VERITAS? A Modular Framework for Archival Document Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Bassanini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ludovico</namePart>
<namePart type="family">Biancardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfio</namePart>
<namePart type="family">Ferrara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Gamberini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Picascia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Folco</namePart>
<namePart type="family">Vaglienti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Grisot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Blochowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The digitisation of historical documents has traditionally been conceived as a process limited to character-level transcription, producing flat text that lacks the structural and semantic information necessary for substantive computational analysis. We present VERITAS (Vision-Enhanced Reading, Interpretation, and Transcription of Archival Sources), a modular, model-agnostic framework that reconceptualises digitisation as an integrated workflow encompassing transcription, layout analysis, and semantic enrichment. The pipeline is organised into four stages—Preprocessing, Extraction, Refinement, and Enrichment—and employs a schema-driven architecture that allows researchers to declaratively specify their extraction objectives. We evaluate VERITAS on the critical edition of Bernardino Corio’s Storia di Milano, a Renaissance chronicle of over 1,600 pages. Results demonstrate that the pipeline achieves a 67.6% relative reduction in word error rate compared to a commercial OCR baseline, with a threefold reduction in end-to-end processing time when accounting for manual correction. We further illustrate the downstream utility of the pipeline’s output by querying the transcribed corpus through a retrieval-augmented generation system, demonstrating its capacity to support historical inquiry.</abstract>
<identifier type="citekey">bassanini-etal-2026-quid</identifier>
<identifier type="doi">10.63317/3ec9hbgdgs8x</identifier>
<location>
<url>https://aclanthology.org/2026.llms4ssh-1.6/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>57</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quid est VERITAS? A Modular Framework for Archival Document Analysis
%A Bassanini, Leonardo
%A Biancardi, Ludovico
%A Ferrara, Alfio
%A Gamberini, Andrea
%A Picascia, Sergio
%A Vaglienti, Folco
%Y Montejo-Raez, Arturo
%Y Grisot, Cristina
%Y Blochowiak, Joanna
%Y Ljubešić, Nikola
%Y Battaner, Elena
%Y Rigau, German
%S Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca (Spain)
%F bassanini-etal-2026-quid
%X The digitisation of historical documents has traditionally been conceived as a process limited to character-level transcription, producing flat text that lacks the structural and semantic information necessary for substantive computational analysis. We present VERITAS (Vision-Enhanced Reading, Interpretation, and Transcription of Archival Sources), a modular, model-agnostic framework that reconceptualises digitisation as an integrated workflow encompassing transcription, layout analysis, and semantic enrichment. The pipeline is organised into four stages—Preprocessing, Extraction, Refinement, and Enrichment—and employs a schema-driven architecture that allows researchers to declaratively specify their extraction objectives. We evaluate VERITAS on the critical edition of Bernardino Corio’s Storia di Milano, a Renaissance chronicle of over 1,600 pages. Results demonstrate that the pipeline achieves a 67.6% relative reduction in word error rate compared to a commercial OCR baseline, with a threefold reduction in end-to-end processing time when accounting for manual correction. We further illustrate the downstream utility of the pipeline’s output by querying the transcribed corpus through a retrieval-augmented generation system, demonstrating its capacity to support historical inquiry.
%R 10.63317/3ec9hbgdgs8x
%U https://aclanthology.org/2026.llms4ssh-1.6/
%U https://doi.org/10.63317/3ec9hbgdgs8x
%P 57-66
Markdown (Informal)
[Quid est VERITAS? A Modular Framework for Archival Document Analysis](https://aclanthology.org/2026.llms4ssh-1.6/) (Bassanini et al., LLMs4SSH 2026)
ACL
- Leonardo Bassanini, Ludovico Biancardi, Alfio Ferrara, Andrea Gamberini, Sergio Picascia, and Folco Vaglienti. 2026. Quid est VERITAS? A Modular Framework for Archival Document Analysis. In Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026, pages 57–66, Palma de Mallorca (Spain). ELRA Language Resources Association (ELRA).